{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T08:24:25Z","timestamp":1778574265552,"version":"3.51.4"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9414560","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"6783-6787","source":"Crossref","is-referenced-by-count":91,"title":["Emformer: Efficient Memory Transformer Based Acoustic Model for Low Latency Streaming Speech Recognition"],"prefix":"10.1109","author":[{"given":"Yangyang","family":"Shi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongqiang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chunyang","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ching-Feng","family":"Yeh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Julian","family":"Chan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Frank","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Duc","family":"Le","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mike","family":"Seltzer","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","first-page":"2345","article-title":"Sequence-discriminative training of deep neural networks","volume":"2013","author":"vesely","year":"2013","journal-title":"InterSpeech"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-2012"},{"key":"ref30","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053896"},{"key":"ref11","article-title":"Transformer-Transducer: End-to-End Speech Recognition with Self-Attention","author":"yeh","year":"2019"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682539"},{"key":"ref14","article-title":"Fast, Simpler and More Accurate Hybrid ASR Systems Using Wordpieces","author":"zhang","year":"2020","journal-title":"InterSpeech"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462497"},{"key":"ref16","article-title":"TransformerBased Acoustic Modeling for Hybrid Speech Recognition","author":"wang","year":"2019","journal-title":"ICASSP"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054476"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2079"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682954"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref4","article-title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","author":"raffel","year":"2019"},{"key":"ref27","article-title":"Audio augmentation for speech recognition","author":"ko","year":"2015","journal-title":"InterSpeech"},{"key":"ref3","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume":"1","author":"devlin","year":"2019","journal-title":"NAACL"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003750"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052964"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462506"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1107"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1910"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1285"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1292"},{"key":"ref1","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"NIPS"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2638"},{"key":"ref22","article-title":"Transformer in action: a comparative study of transformer-based acoustic model for large scale speech recognition applications","author":"wang","year":"2021","journal-title":"ICASSP"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref24","article-title":"Developing Real-time Streaming Transformer Transducer for Speech Recognition on Large-scale Dataset","author":"chen","year":"2020"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1363"},{"key":"ref26","first-page":"1","article-title":"The Kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"ASRU"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003972"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Toronto, ON, Canada","start":{"date-parts":[[2021,6,6]]},"end":{"date-parts":[[2021,6,11]]}},"container-title":["ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9413349\/9413350\/09414560.pdf?arnumber=9414560","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:40:51Z","timestamp":1652197251000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9414560\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9414560","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}